Figure 2 - uploaded by Ankush Jamthikar
Content may be subject to copyright.
The cross-sectional view of the blood vessels of the (A) young and (B) aged person (Courtesy AtherpPointTM, Roseville, USA).
Source publication
Background:
Vascular age (VA) has recently emerged for CVD risk assessment and can either be computed using conventional risk factors (CRF) or by using carotid intima-media thickness (cIMT) derived from carotid ultrasound (CUS). This study investigates a novel method of integrating both CRF and cIMT for estimating VA [so-called integrated VA (IVA)...
Contexts in source publication
Context 1
... process further results in the aging of the artery. The crosssectional view can be visualized in Figure 2 which depicts the difference in vascular geometry of the young and the elderly persons. Vascular aging increases the fibrosis that results in increased thickness of the intimal and medial layers (47). ...
Context 2
... process further results in the aging of the artery. The crosssectional view can be visualized in Figure 2 which depicts the difference in vascular geometry of the young and the elderly persons. Vascular aging increases the fibrosis that results in increased thickness of the intimal and medial layers (47). ...
Similar publications
Machine learning (ML)-based algorithms for cardiovascular disease (CVD) risk assessment have shown promise in clinical decisions. However, they usually predict binary events using only conventional risk factors. Our overall goal was to develop the “multiclass machine learning (MCML)-based algorithms” (labelled as AtheroEdge 3.0ML) and assess whethe...
Citations
... CVD is caused by many things, including genetic, metabolomic, environmental, behavioural, and lifestyle factors [6,7]. Although traditional risk factors such as age, gender, high cholesterol, high blood pressure [8], smoking, and comorbidities like diabetes mellitus [9], obesity [10], and hypertension [11,12] are commonly used risk factors for predicting CVD risk, laboratory-based biomarkers are not always feasible, particularly in developing countries with resource constraints [13,14]. Also, most scoring systems for CVD risk were made for Caucasians, and their validity and usefulness in other ethnic groups are still unknown [15]. ...
... The medical imaging field has noted the progress made in ML and DL [125][126][127][128]. Deep neural networks (DNNs), a subset of DL, work like the human brain [39,117,129]. AI has been used in recent studies to figure out the risk of CVD using RBBM [11,12,38,[130][131][132][133][134] and GBBM [33,135,136] frameworks. DL is becoming more popular because (i) it automatically extracts features [137], (ii) it can fuse with different ML configurations for classification [117,138], (iii) it uses UNet and Hybrid UNet-based DL strategies for segmentation [43,119], and (iv) Lastly, it gives more accurate segmentation and solo or ensemblebased classification because it can go through forward and backward propagation by reducing the loss using different kinds of loss functions [74]. ...
... However, all the studies mentioned the role of OBBM and LBBM in CVD risk. Five studies adopted DL technologies [27,41,75,196,198,199], while eight studies used ML [11,131,197,202], and two studies used HDL [143,201]. Only four studies discussed the risk of bias (RoB) [75,143,202]. ...
Background:
Cardiovascular disease (CVD) is challenging to diagnose and treat since symptoms appear late during the progression of atherosclerosis. Conventional risk factors alone are not always sufficient to properly categorize at-risk patients, and clinical risk scores are inadequate in predicting cardiac events. Integrating genomic-based biomarkers (GBBM) found in plasma/serum samples with novel non-invasive radiomics-based biomarkers (RBBM) such as plaque area, plaque burden, and maximum plaque height can improve composite CVD risk prediction in the pharmaceutical paradigm. These biomarkers consider several pathways involved in the pathophysiology of atherosclerosis disease leading to CVD.
Objective:
This review proposes two hypotheses: (i) The composite biomarkers are strongly correlated and can be used to detect the severity of CVD/Stroke precisely, and (ii) an explainable artificial intelligence (XAI)-based composite risk CVD/Stroke model with survival analysis using deep learning (DL) can predict in preventive, precision, and personalized (aiP3) framework benefiting the pharmaceutical paradigm.
Method:
The PRISMA search technique resulted in 214 studies assessing composite biomarkers using radiogenomics for CVD/Stroke. The study presents a XAI model using AtheroEdgeTM 4.0 to determine the risk of CVD/Stroke in the pharmaceutical framework using the radiogenomics biomarkers.
Conclusions:
Our observations suggest that the composite CVD risk biomarkers using radiogenomics provide a new dimension to CVD/Stroke risk assessment. The proposed review suggests a unique, unbiased, and XAI model based on AtheroEdgeTM 4.0 that can predict the composite risk of CVD/Stroke using radiogenomics in the pharmaceutical paradigm.
... This fusion was used for determining the 10-year CVD risk [118,123,124]. Each slice of the pie represents one of the conventional risk variables or carotid imaging phenotypes that contributes independently to the 10-year CVD risk [125][126][127][128][129][130][131]. ...
Motivation: The price of medical treatment continues to rise due to (i) an increasing population; (ii) an aging human growth; (iii) disease prevalence; (iv) a rise in the frequency of patients that utilize health care services; and (v) increase in the price. Objective: Artificial Intelligence (AI) is already well-known for its superiority in various healthcare applications, including the segmentation of lesions in images, speech recognition, smartphone personal assistants, navigation, ride-sharing apps, and many more. Our study is based on two hypotheses: (i) AI offers more economic solutions compared to conventional methods; (ii) AI treatment offers stronger economics compared to AI diagnosis. This novel study aims to evaluate AI technology in the context of healthcare costs, namely in the areas of diagnosis and treatment, and then compare it to the traditional or non-AI-based approaches. Methodology: PRISMA was used to select the best 200 studies for AI in healthcare with a primary focus on cost reduction, especially towards diagnosis and treatment. We defined the diagnosis and treatment architectures, investigated their characteristics, and categorized the roles that AI plays in the diagnostic and therapeutic paradigms. We experimented with various combinations of different assumptions by integrating AI and then comparing it against conventional costs. Lastly, we dwell on three powerful future concepts of AI, namely, pruning, bias, explainability, and regulatory approvals of AI systems. Conclusions: The model shows tremendous cost savings using AI tools in diagnosis and treatment. The economics of AI can be improved by incorporating pruning, reduction in AI bias, explainability, and regulatory approvals.
... In the non-AI-based methods for CVD/stroke the risk was determined by computing the digital total of all the normalized risk values for the image-based biomarkers and then compartmentalized into different risk classes such as no-risk, low-risk, low-moderate risk, high-moderate risk, low-of-high risk, and high-of-high risk. This was computed using the AtheroEdge™ 2.0 system (AtheroPoint, Roseville, CA, USA) [36, 220,221,[258][259][260][261][262][263][264][265]. Imagebased biomarkers, such as TPA, have shown to have a strong link with eGFR [266], and thus AI-based solution have adapted the usage of TPA in the modeling process. ...
Background and Motivation: Parkinson’s disease (PD) is one of the most serious, non-curable, and expensive to treat. Recently, machine learning (ML) has shown to be able to predict cardiovascular/stroke risk in PD patients. The presence of COVID-19 causes the ML systems to become severely non-linear and poses challenges in cardiovascular/stroke risk stratification. Further, due to comorbidity, sample size constraints, and poor scientific and clinical validation techniques, there have been no well-explained ML paradigms. Deep neural networks are powerful learning machines that generalize non-linear conditions. This study presents a novel investigation of deep learning (DL) solutions for CVD/stroke risk prediction in PD patients affected by the COVID-19 framework. Method: The PRISMA search strategy was used for the selection of 292 studies closely associated with the effect of PD on CVD risk in the COVID-19 framework. We study the hypothesis that PD in the presence of COVID-19 can cause more harm to the heart and brain than in non-COVID-19 conditions. COVID-19 lung damage severity can be used as a covariate during DL training model designs. We, therefore, propose a DL model for the estimation of, (i) COVID-19 lesions in computed tomography (CT) scans and (ii) combining the covariates of PD, COVID-19 lesions, office and laboratory arterial atherosclerotic image-based biomarkers, and medicine usage for the PD patients for the design of DL point-based models for CVD/stroke risk stratification. Results: We validated the feasibility of CVD/stroke risk stratification in PD patients in the presence of a COVID-19 environment and this was also verified. DL architectures like long short-term memory (LSTM), and recurrent neural network (RNN) were studied for CVD/stroke risk stratification showing powerful designs. Lastly, we examined the artificial intelligence bias and provided recommendations for early detection of CVD/stroke in PD patients in the presence of COVID-19.Conclusion: The DL is a very powerful tool for predicting CVD/stroke risk in PD patients affected by COVID-19.
... Individuals easily understand vascular age, so it would be better to find their CVD risk [1]. While CIMT and CS have been utilized to develop a vascular age, few data are available comparing these two modalities [17]. The goal of the present study was to compare the results of vascular age assessment in individual patients using both CS and CIMT. ...
... In our study, hence vascular age based on CS and CIMT was well matched; the mean vascular age was less than chronological age, in contrast to the survey by Khalil. In other studies comparing vascular age and chronological age (Although none have surveyed the correlation of age derived by CIMT and CS), mean vascular age has shown more than chronological age [17,[25][26][27][28]. Our different results could be related to our patient selection bias. ...
Background:
Considering the importance of vascular age in the risk assessment of cardiovascular events and the presence of different methods for its estimation, this study aims to evaluate and compare vascular age according to coronary artery calcium scoring (CACS) and carotid ultrasonography.
Methods:
This study was conducted in Isfahan on patients who underwent CACS and carotid intima-media thickness (CIMT) assessments within 30 days. In patients who were candidates for CACS, calcium score was measured, then they were invited for carotid ultrasonography, and CIMT was measured. Vascular age was estimated based on these methods using available formulas.
Results:
In this study, 115 patients were enrolled. (Male 52.2%, female 47.8%). The mean chronological age was 59.08 ± 14.90 years old. The mean calcium score (CS) of patients was 48.23 ± 63.34. Mean CIMT was 0.73 ± 0.15 mm. The mean vascular age derived by CS and CIMT was 58.64 ± 12.63 and 53.99 ± 17.53 years, respectively. The vascular age obtained by CS was directly related to vascular age based on CIMT (P-value < 0.05).
Conclusion:
Calcium score is as helpful as CIMT for vascular age estimation.
... Two popular carotid ultrasound image-based phenotypes (CUSIP) such as carotid intima-media thickness and carotid plaque area are considered as the surrogate indicator of coronary artery disease (CAD) [13][14][15][16][17][18][19][20]. For example, RA patients reportedly have higher values of this CUSIP compared to non-RA patients and, therefore, these atherosclerotic plaque-based phenotypes could be used for an accurate CVD risk assessment [21][22][23][24]. There are two major drawbacks with CCVRC (i) they do not integrate CUSIP in their risk prediction model and (ii) they do not handle the complex nonlinear association between several CVD risk factors and the CVE endpoints [12]. ...
... We used 3 types of classifiers such as random forest (RF) [42], support vector machine with the radial basis function (SVMrbf) [43,44], and linear discriminant analysis (LDA) [45,46] to perform CVD-CR and CVD-3YFU using the combination of 46 covariates and CVE (as ground truth) in the ML framework. The theory and the optimization parameters of these classifiers are shown in Appendix B. The performance evaluation metrics are shown in Appendix C. Further, we compare the ML calculators (RF, SVMrbf, and LDA) against the conventional calculators (FRS, SCORE, and ASCVD) [23,47]. ...
... The performance of all three ML-based classifiers (LDA, SVMrbf, and RF) and all three CCVRC calculators (FRS, SCORE, and ASCVD) [23,47] was assessed using various metrics such as sensitivity, specificity, false-positive rate (FPR), false-negative rate (FNR), positive predictive value (PPV), negative predictive value (NPV), accuracy and areaunder-the-curve (AUC). The AUC score for all the matrices Supplementary Information The online version contains supplementary material available at https:// doi. ...
The study proposes a novel machine learning (ML) paradigm for cardiovascular disease (CVD) detection in individuals at medium to high cardiovascular risk using data from a Greek cohort of 542 individuals with rheumatoid arthritis, or diabetes mellitus, and/or arterial hypertension, using conventional or office-based, laboratory-based blood biomarkers and carotid/femoral ultrasound image-based phenotypes. Two kinds of data (CVD risk factors and presence of CVD—defined as stroke, or myocardial infarction, or coronary artery syndrome, or peripheral artery disease, or coronary heart disease) as ground truth, were collected at two-time points: (i) at visit 1 and (ii) at visit 2 after 3 years. The CVD risk factors were divided into three clusters (conventional or office-based, laboratory-based blood biomarkers, carotid ultrasound image-based phenotypes) to study their effect on the ML classifiers. Three kinds of ML classifiers (Random Forest, Support Vector Machine, and Linear Discriminant Analysis) were applied in a two-fold cross-validation framework using the data augmented by synthetic minority over-sampling technique (SMOTE) strategy. The performance of the ML classifiers was recorded. In this cohort with overall 46 CVD risk factors (covariates) implemented in an online cardiovascular framework, that requires calculation time less than 1 s per patient, a mean accuracy and area-under-the-curve (AUC) of 98.40% and 0.98 (p < 0.0001) for CVD presence detection at visit 1, and 98.39% and 0.98 (p < 0.0001) at visit 2, respectively. The performance of the cardiovascular framework was significantly better than the classical CVD risk score. The ML paradigm proved to be powerful for CVD prediction in individuals at medium to high cardiovascular risk.
... A 10-year risk prediction model, atherosclerosis CVD (ASCVD) developed by American College of Cardiology/American Heart Association, was used in their research. Furthermore, we compared our system with these studies, and found that our study has been solely focused upon the effect of ethnicity on the performance of the system [64]. ...
Background:
The early detection of carotid wall plaque is recommended in the prevention of cardiovascular disease (CVD) in moderate-risk patients. Previous techniques for B-mode carotid atherosclerotic wall plaque segmentation used artificial intelligence (AI) methods on monoethnic databases, where training and testing are from the "same" ethnic group ("Seen AI"). Therefore, the versatility of the system is questionable. This is the first study of its kind that uses the "Unseen AI" paradigm where training and testing are from "different" ethnic groups. We hypothesized that deep learning (DL) models should perform in 10% proximity between "Unseen AI" and "Seen AI".
Methodology:
Two cohorts from multi-ethnic groups (330 Japanese and 300 Hong Kong (HK)) were used for the validation of our hypothesis. We used a four-layered UNet architecture for the segmentation of the atherosclerotic wall with low plaque. "Unseen AI" (training: Japanese, testing: HK or vice versa) and "Seen AI" experiments (single ethnicity or mixed ethnicity) were performed. Evaluation was conducted by measuring the wall plaque area. Statistical tests were conducted for its stability and reliability.
Results:
When using the UNet DL architecture, the "Unseen AI" pair one (Training: 330 Japanese and Testing: 300 HK), the mean accuracy, dice-similarity, and correlation-coefficient were 98.55, 78.38, and 0.80 (p < 0.0001), respectively, while for "Unseen AI" pair two (Training: 300 HK and Testing: 330 Japanese), these were 98.67, 82.49, and 0.87 (p < 0.0001), respectively. Using "Seen AI", the same parameters were 99.01, 86.89 and 0.92 (p < 0.0001), respectively.
Conclusion:
We demonstrated that "Unseen AI" was in close proximity (<10%) to "Seen AI", validating our DL model for low atherosclerotic wall plaque segmentation. The online system runs < 1 s.
... Subclinical carotid atherosclerosis and its severity are associated with the development of coronary and cerebral cardiovascular disease, 16 the progression of cognitive deficit 14 and mortality. 34,35 It allows estimating the "arterial age" 36,37,38 and monitoring its evolution. 16 The visualization by patients of their subclinical carotid atherosclerosis, detected by carotid ultrasound, can improve adherence to lifestyle modifications and medication. ...
... COVID-19 symptoms of the patients and seriousness have helped to decide which imaging technique is most appropriate: Portable and non-portable [23] . In COVID-19 patients, non-invasive carotid ultrasound may be adopted for low-risk patients to investigate the presence of carotid atherosclerotic plaque [182,183] , which is also considered as a surrogate marker CVD [184][185][186] and also used for CVD risk assessment in diabetic March 15, 2021 Volume 12 Issue 3 patients [187][188][189][190][191][192][193][194][195][196][197] . Similarly, magnetic resonance imaging and X-rays can be useful for screening of medium risk patients [198][199][200] . ...
... Several studies used ultrasound to detect the rupture-prone atherosclerotic plaque and the tissue characterization of such plaque for the prevention of future cardiac events [205][206][207] . Furthermore, studies have used ultrasound-based imaging techniques for CVD risk assessment in patients with diabetes [187][188][189]191,193,195,196,[208][209][210][211][212] and, thus, could also be adopted for diabetic patients with COVID-19. Several other imaging-based studies have shown the interaction of plaque measurements in diabetes patients [196,211,212] . ...
Coronavirus disease 2019 (COVID-19) is a global pandemic where several comorbidities have been shown to have a significant effect on mortality. Patients with diabetes mellitus (DM) have a higher mortality rate than non-DM patients if they get COVID-19. Recent studies have indicated that patients with a history of diabetes can increase the risk of severe acute respiratory syndrome coronavirus 2 infection. Additionally, patients without any history of diabetes can acquire new-onset DM when infected with COVID-19. Thus, there is a need to explore the bidirectional link between these two conditions, confirming the vicious loop between "DM/COVID-19". This narrative review presents (1) the bidirectional association between the DM and COVID-19, (2) the manifestations of the DM/COVID-19 loop leading to cardiovascular disease, (3) an understanding of primary and secondary factors that influence mortality due to the DM/COVID-19 loop, (4) the role of vitamin-D in DM patients during COVID-19, and finally, (5) the monitoring tools for tracking atherosclerosis burden in DM patients during COVID-19 and "COVID-triggered DM" patients. We conclude that the bidirectional nature of DM/COVID-19 causes acceleration towards cardiovascular events. Due to this alarming condition, early monitoring of atherosclerotic burden is required in "Diabetes patients during COVID-19" or "new-onset Diabetes triggered by COVID-19 in Non-Diabetes patients".
Background
Cardiovascular risk (CVR) in people with T1DM is assessed using ESC/EASD criteria. However, recent studies have suggested methods that are more accurate for T1DM, such as the Steno Type 1 Risk Engine (ST1RE), vascular age (VA) based on common carotid intima-media thickness (cIMT), and arterial stiffness (AS). We aimed to investigate the association between VA, AS, ST1RE, and ESC/EASD 2019 CVR categories in people with T1DM.
Methods
The study group comprised T1DM adults aged 18–45 years with a diabetes duration of at least 5 years and without cardiovascular disease. Medical history, anthropometrical features, and laboratory results were collected and used to calculate the 10-year CVR using ST1RE. The cIMT automatic measurement was performed. Based on cIMT, VA was calculated and used instead of chronological age to estimate the modified ST1RE score. We assessed AS by measuring the 24-hour aortic pulse wave velocity (PWV Ao) with a brachial oscillometric device (Arteriograph 24). The participants were divided into 3 CVR categories using ESC/EASD criteria and modified ST1RE scores.
Results
Sixty-one individuals with a median age of 30.0 (25.0–36.0) years and a diabetes duration of 15.0 (9.0–20.0) years were enrolled. PWV Ao was positively related to VA (Rs = 0.31; p = 0.01) and the modified ST1RE score (Rs = 0.36; p < 0.01). Modified ST1RE categories showed significantly higher agreement (κ = 0.14; p = 0.02) with the ESC/EASD 2019 criteria than the standard ST1RE (κ = 0.00; p = 0.92). The PWV Ao increased with each ESC/EASD 2019 category – 6.62 (6.51–7.32) m/s at moderate risk, 7.50 (7.00–8.05) m/s at high risk, and 8.33 (7.52–9.21) m/s at very high risk (p = 0.02). The multiple logistic regression model revealed that PWV Ao was positively associated with high versus low and moderate CVR based on modified ST1RE (OR = 2.58; 95% CI: 1.04–6.42; p = 0.04). The association was independent of sex, glycated hemoglobin, diabetes duration, the presence of diabetic complications, and BMI.
Conclusions
Among individuals with T1DM, AS and VA are positively associated with ESC/EASD 2019 criteria and both ST1RE scores. CVR categories based on ST1RE with vascular instead of chronological age have better agreement with the ESC/EASD 2019 criteria.
